R Notebook

To Do:

1. Load

2. Key variables

3. descriptives –> how many countries, participants

4. How to visualize? do we want to do the visualization? Per Country or all together // coulors? etc.

5. What do we want to present?

• Presentation 19.12.2023
• finalise presentation 05.12.2023 with rui
• Send presentation 27.11.2023
• Presentation content
  • why we do this
  • research gap
  • method
  • results
  • challenges
  • conclusion —> Do the Presentation on GoogleSlides
• cancel 12.12.2023 und 19.12.2023

etc. …..

#Install packages

install.packages("haven")

trying URL 'https://cran.rstudio.com/bin/macosx/big-sur-arm64/contrib/4.3/haven_2.5.3.tgz'
Content type 'application/x-gzip' length 1132879 bytes (1.1 MB)
==================================================
downloaded 1.1 MB

The downloaded binary packages are in
    /var/folders/8t/cf05ypcs56z1d0qh3cl43l880000gn/T//RtmpgK7aj1/downloaded_packages

#Load packages

library(data.table)
library(tidyr)
library(haven)

#Add data WV6

WV6_data <- load("/Users/laurabazzigher/Documents/GitHub/risk_wvs/data/dataset/WV6_dataset_wave_5_6/WV6_Data_R_v20201117.rdata") 
WV6_data <- WV6_Data_R_v20201117 
print(WV6_data)

#Name the variables

data6 = WV6_Data_R_v20201117[, c("V1", "V2", "V10", "V23", "V70", "V71","V72","V73", "V74B", "V75", "V76", "V77", "V78",  "V79", "V147", "V149","V198", "V199", "V201", "V208","V209", "V210", "V240", "V242", "V248", "V229", "V57", "V58")]

names(data6) = c("v1_wave", "v2_country", "v10_happyness", "v23_satisfaction", "v70_creativity", "v71_money", "v72_security", "v73_goodtime", "v74b_help", "v75_success", "v76_risk", "v77_proper", "v78_environment", "v79_tradition", "v147_religion", "v149_hell", "v198_gov_benefits", "v199_fare_public_transportation", "v201_cheating_taxes", "v208_beating_wife", "v209_beating_children", "v210_violence", "v240_sex", "v242_age", "v248_education", "v229_employed", "v57_married", "v58_children")

#Exlusion of participants which no info about sex, age, education, employment status, marital status, or number of children

data6 = subset(data6, v76_risk > 0 & v240_sex > 0 & v242_age >0 & v248_education > 0 & v229_employed > 0 & v57_married > 0 & v58_children >= 0)

#New column for variable “creativity”

# Erstellen einer neuen Zeile für die Variable 
data6$creativity <- NA

# Zuordnen der Werte
data6$creativity[data6$v70_creativity == 1] <- "Very much like me"
data6$creativity[data6$v70_creativity == 2] <- "Like me"
data6$creativity[data6$v70_creativity == 3] <- "Somewhat like me"
data6$creativity[data6$v70_creativity == 4] <- "A little like me"
data6$creativity[data6$v70_creativity == 5] <- "Not like me"
data6$creativity[data6$v70_creativity == 6] <- "Not at all like me"

#New column for variable “security”

data6$creativity <- NA

data6$security[data6$v72_security == 1] <- "Very much like me"
data6$security[data6$v72_security == 2] <- "Like me"
data6$security[data6$v72_security == 3] <- "Somewhat like me"
data6$security[data6$v72_security == 4] <- "A little like me"
data6$security[data6$v72_security == 5] <- "Not like me"
data6$security[data6$v72_security == 6] <- "Not at all like me"

#New column for variable “goodtime”

data6$goodtime <- NA

data6$goodtime[data6$v73_goodtime == 1] <- "Very much like me"
data6$goodtime[data6$v73_goodtime == 2] <- "Like me"
data6$goodtime[data6$v73_goodtime == 3] <- "Somewhat like me"
data6$goodtime[data6$v73_goodtime == 4] <- "A little like me"
data6$goodtime[data6$v73_goodtime == 5] <- "Not like me"
data6$goodtime[data6$v73_goodtime == 6] <- "Not at all like me"

#New column for variable “money”

data6$money <- NA

data6$money[data6$v70_creativity == 1] <- "Very much like me"
data6$money[data6$v70_creativity == 2] <- "Like me"
data6$money[data6$v70_creativity == 3] <- "Somewhat like me"
data6$money[data6$v70_creativity == 4] <- "A little like me"
data6$money[data6$v70_creativity == 5] <- "Not like me"
data6$money[data6$v70_creativity == 6] <- "Not at all like me"

#New column for variable “help”

data6$help <- NA

data6$help[data6$v74b_help == 1] <- "Very much like me"
data6$help[data6$v74b_help == 2] <- "Like me"
data6$help[data6$v74b_help == 3] <- "Somewhat like me"
data6$help[data6$v74b_help == 4] <- "A little like me"
data6$help[data6$v74b_help == 5] <- "Not like me"
data6$help[data6$v74b_help == 6] <- "Not at all like me"

#New column for variable “success”

data6$success <- NA

data6$success[data6$v75_success == 1] <- "Very much like me"
data6$success[data6$v75_success == 2] <- "Like me"
data6$success[data6$v75_success == 3] <- "Somewhat like me"
data6$success[data6$v75_success == 4] <- "A little like me"
data6$success[data6$v75_success == 5] <- "Not like me"
data6$success[data6$v75_success == 6] <- "Not at all like me"

#New column for variable “risk”

data6$risk <- NA

# Zuordnen der Werte
data6$risk[data6$v76_risk == 1] <- "Very much like me"
data6$risk[data6$v76_risk == 2] <- "Like me"
data6$risk[data6$v76_risk == 3] <- "Somewhat like me"
data6$risk[data6$v76_risk == 4] <- "A little like me"
data6$risk[data6$v76_risk == 5] <- "Not like me"
data6$risk[data6$v76_risk == 6] <- "Not at all like me"

#New column for variable “proper”

data6$proper <- NA

data6$proper[data6$v77_proper == 1] <- "Very much like me"
data6$proper[data6$v77_proper == 2] <- "Like me"
data6$proper[data6$v77_proper == 3] <- "Somewhat like me"
data6$proper[data6$v77_proper == 4] <- "A little like me"
data6$proper[data6$v77_proper == 5] <- "Not like me"
data6$proper[data6$v77_proper == 6] <- "Not at all like me"

#New column for variable “environment”

data6$environment <- NA

data6$environment[data6$v78_environment == 1] <- "Very much like me"
data6$environment[data6$v78_environment == 2] <- "Like me"
data6$environment[data6$v78_environment == 3] <- "Somewhat like me"
data6$environment[data6$v78_environment == 4] <- "A little like me"
data6$environment[data6$v78_environment == 5] <- "Not like me"
data6$environment[data6$v78_environment == 6] <- "Not at all like me"

#New column for variable “tradition”

data6$tradition <- NA

data6$tradition[data6$v79_tradition == 1] <- "Very much like me"
data6$tradition[data6$v79_tradition == 2] <- "Like me"
data6$tradition[data6$v79_tradition == 3] <- "Somewhat like me"
data6$tradition[data6$v79_tradition == 4] <- "A little like me"
data6$tradition[data6$v79_tradition == 5] <- "Not like me"
data6$tradition[data6$v79_tradition == 6] <- "Not at all like me"

#New column for variable “satisfaction”

data6$satisfaction <- NA

data6$satisfaction[data6$v57_married == 1] <- "Very happy"
data6$satisfaction[data6$v10_happyness == 2] <- "Rather happy"
data6$satisfaction[data6$v10_happyness == 3] <- "Not very happy"
data6$satisfaction[data6$v10_happyness == 4] <- "Not at all happy"

#New column for variable “marrital status”

# Erstellen einer neuen Zeile für die Variable "verheiratet"
data6$marital_status <- NA

# Zuordnen der Werte
data6$marital_status[data6$v57_married == 1] <- "Married"
data6$marital_status[data6$v57_married == 2] <- "Living together as married"
data6$marital_status[data6$v57_married == 3] <- "Divorced"
data6$marital_status[data6$v57_married == 4] <- "Separated"
data6$marital_status[data6$v57_married == 5] <- "Widowed"
data6$marital_status[data6$v57_married == 6] <- "Single"

#New column for variable “religion”

# Erstellen einer neuen Zeile für die Variable 
data6$religion <- NA

# Zuordnen der Werte
data6$religion[data6$v147_religion == 1] <- "A religious person"
data6$religion[data6$v147_religion == 2] <- "Not a religious person"
data6$religion[data6$v147_religion == 3] <- "An atheist"

#Categorical age variable (for example, to plot response frequencies by category)

data6$agecat <- NA  # Create an empty column 'agecat'

data6$agecat[data6$v242_age < 20] = "15-19"
data6$agecat[data6$v242_age >= 20 & data6$v242_age < 30] = "20-29"
data6$agecat[data6$v242_age >= 30 & data6$v242_age < 40] = "30-39"
data6$agecat[data6$v242_age >= 40 & data6$v242_age < 50] = "40-49"
data6$agecat[data6$v242_age >= 50 & data6$v242_age < 60] = "50-59"
data6$agecat[data6$v242_age >= 60 & data6$v242_age < 70] = "60-69"
data6$agecat[data6$v242_age >= 70 & data6$v242_age < 80] = "70-79"
data6$agecat[data6$v242_age >= 80] = "80+"

#New column for variable “sex”

# Erstellen einer neuen Zeile für die Variable 
data6$sex <- NA

# Zuordnen der Werte
data6$sex[data6$v240_sex == 1] <- "male"
data6$sex[data6$v240_sex == 2] <- "female"

#Number of countries

length(unique(data6$v2_country)) 

#Number of participants

nrow(data6) 

#Range of age

range(data6$v242_age) 

#Table about gender

table(data6$sex)

Scatterplot of Age vs. Risk with ggplot

data_df <- data.frame(Age = data6$v242_age, Risk = data6$v76_risk) # Convert data into a data frame.

ggplot(data_df, aes(x = Age, y = Risk)) +
  geom_point(color = "blue", size = 1) +
  labs(title = "Scatterplot of Age vs. Risk",
       x = "Age",
       y = "Risk")

Histogramm for Age

hist(data6$v242_age, 
     main="Häufigkeitsverteilung des Alters",
     xlab="Alter",
     ylab="Häufigkeit",
     col="blue")

Overview of religion vs. Risk

cross_table <- table(data6$religion, data6$risk)
print(cross_table)

                        
                         A little like me Like me Not at all like me Not like me Somewhat like me
  A religious person                 8338    8617               8905       12174            10144
  An atheist                          718     612                507        1031              689
  Not a religious person             3790    2887               2851        4944             3678
                        
                         Very much like me
  A religious person                  6643
  An atheist                           335
  Not a religious person              1804

#compare the groups religion and risk ### Because of the different sample sizes to compare the groups, the data is normalised and changed into % to compare the groups.

# Summe of participants in each group
sum_religious <- sum(c(8338, 718, 3790))
sum_atheist <- sum(c(8617, 612, 2887))
sum_not_religious <- sum(c(8905, 507, 2851))

# normalising data
normalized_data <- data.frame(
  Religion = c("A religious person", "An atheist", "Not a religious person"),
  `A little like me` = c(8338/sum_religious, 718/sum_atheist, 3790/sum_not_religious),
  `Like me` = c(8617/sum_religious, 612/sum_atheist, 2887/sum_not_religious),
  `Not at all like me` = c(8905/sum_religious, 507/sum_atheist, 2851/sum_not_religious),
  `Not like me` = c(12174/sum_religious, 1031/sum_atheist, 4944/sum_not_religious),
  `Somewhat like me` = c(10144/sum_religious, 689/sum_atheist, 3678/sum_not_religious),
  `Very much like me` = c(6643/sum_religious, 335/sum_atheist, 1804/sum_not_religious)
)

# Convert data to long format
normalized_data_long <- tidyr::gather(normalized_data, key = "Risk", value = "Percentage", -Religion)

# Create a bar chart
ggplot(normalized_data_long, aes(x = Religion, y = Percentage, fill = Risk)) +
  geom_bar(stat = "identity", position = "dodge") +
  labs(title = "Normalized Risk Distribution by Religion",
       x = "Religion",
       y = "Percentage")